An overview of statistical learning theory Export

@article{citeulike:353426, abstract = {Statistical learning theory was introduced in the late 1960's. Until the 1990's it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990's new types of learning algorithms (called support vector machines) based on the developed theory were proposed. This made statistical learning theory not only a tool for the theoretical analysis but also a tool for creating practical algorithms for estimating multidimensional functions. This article presents a very general overview of statistical learning theory including both theoretical and algorithmic aspects of the theory. The goal of this overview is to demonstrate how the abstract learning theory established conditions for generalization which are more general than those discussed in classical statistical paradigms and how the understanding of these conditions inspired new algorithmic approaches to function estimation problems}, author = {Vapnik, V. N.}, citeulike-article-id = {353426}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/72.788640}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=788640}, citeulike-linkout-2 = {http://www.cs.orst.edu/~bulatov/papers/vapnik-statistical.pdf}, doi = {10.1109/72.788640}, journal = {Neural Networks, IEEE Transactions on}, keywords = {statistical-learning-theory}, number = {5}, pages = {988--999}, posted-at = {2005-10-18 03:32:09}, priority = {2}, title = {An overview of statistical learning theory}, url = {http://dx.doi.org/10.1109/72.788640}, volume = {10}, year = {1999} }

TY - JOUR ID - citeulike:353426 L3 - citeulike-article-id:353426 N2 - Statistical learning theory was introduced in the late 1960's. Until the 1990's it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990's new types of learning algorithms (called support vector machines) based on the developed theory were proposed. This made statistical learning theory not only a tool for the theoretical analysis but also a tool for creating practical algorithms for estimating multidimensional functions. This article presents a very general overview of statistical learning theory including both theoretical and algorithmic aspects of the theory. The goal of this overview is to demonstrate how the abstract learning theory established conditions for generalization which are more general than those discussed in classical statistical paradigms and how the understanding of these conditions inspired new algorithmic approaches to function estimation problems IS - 5 JF - Neural Networks, IEEE Transactions on EP - 999 TI - An overview of statistical learning theory VL - 10 SP - 988 KW - statistical-learning-theory AU - Vapnik, VN PY - 1999/// UR - http://dx.doi.org/10.1109/72.788640 ER -